Related Experiment Video
Updated: Apr 18, 2026
10:28
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
16.6K
Predicting the severity of motor neuron disease progression using electronic health record data with a cloud
Kyung Dae Ko1, Tarek El-Ghazawi1, Dongkyu Kim2
1High-Performance Computing Laboratory (HPCL), The George Washington University, Ashburn, VA, United States.
IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology Proceedings. IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology
|January 13, 2015
Summary
This study introduces a new method for predicting motor neuron disease progression using patient records. The system achieved 66% accuracy in predicting Amyotrophic Lateral Sclerosis (ALS) progression, aiding diagnosis.
Area of Science:
- Neurology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Motor neuron diseases (MNDs) are progressive neurological disorders with no cure, necessitating accurate diagnosis for effective patient management.
- Current diagnostic methods for MNDs, particularly Amyotrophic Lateral Sclerosis (ALS), suffer from high rates of misdiagnosis, with up to 10% false positives and 44% false negatives.
- The lack of precise diagnostic tools hinders timely and appropriate treatment strategies for patients with these debilitating conditions.
Purpose of the Study:
- To develop and implement a novel methodology for profiling specific medical information from patient records to predict the progression of motor neuron diseases.
- To enhance diagnostic accuracy and prognostic capabilities for neurological conditions like ALS.
- To leverage machine learning techniques for analyzing complex clinical data and improving patient outcomes.
Main Methods:
- A new system was developed to extract and profile key medical information from electronic health records.
- The system utilized Apache Mahout's Random Forest classifier, implemented on the Hbase big data platform.
- Medical records were sourced from the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT).
Main Results:
- The implemented system demonstrated a 66% accuracy in predicting the progression of Amyotrophic Lateral Sclerosis (ALS).
- The methodology successfully profiled specific medical information relevant to disease progression from patient records.
- This approach shows promise in improving the accuracy of MND progression prediction compared to existing methods.
Conclusions:
- The developed methodology offers a promising approach for predicting motor neuron disease progression, particularly ALS.
- Utilizing big data platforms and machine learning classifiers can significantly improve the analysis of clinical data for enhanced diagnostic support.
- Further research and validation are warranted to integrate this system into clinical practice for better patient care and management of MNDs.
